paper-with-me

Papers

RegCLR: A Self-Supervised Framework for Tabular Representation Learning in the Wild

2022-11-02 · Weiyao Wang, Byung-Hak Kim, Varun Ganapathi

Recent advances in self-supervised learning (SSL) using large models to learn visual representations from natural images are rapidly closing the gap between the results produced by fully supervised learning and those produced by SSL on downstream vision tasks. Inspired by this advancement and primarily motivated by the emergence of tabular and structured document image applications, we investigate which self-supervised pretraining objectives, architectures, and fine-tuning strategies are most effective. To address these questions, we introduce RegCLR, a new self-supervised framework that combines contrastive and regularized methods and is compatible with the standard Vision Transformer architecture. Then, RegCLR is instantiated by integrating masked autoencoders as a representative example of a contrastive method and enhanced Barlow Twins as a representative example of a regularized method with configurable input image augmentations in both branches. Several real-world table recognition scenarios (e.g., extracting tables from document images), ranging from standard Word and Latex documents to even more challenging electronic health records (EHR) computer screen images, have been shown to benefit greatly from the representations learned from this new framework, with detection average-precision (AP) improving relatively by 4.8% for Table, 11.8% for Column, and 11.1% for GUI objects over a previous fully supervised baseline on real-world EHR screen images.

📄 PDF Abstract BibTeX arXiv:2211.01165

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningSelf-Supervised LearningTable Recognition

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Distributionally robust self-supervised learning for tabular data

2024-10-11 · Shantanu Ghosh, Tiankang Xie, Mikhail Kuznetsov

Machine learning (ML) models trained using Empirical Risk Minimization (ERM) often exhibit systematic errors on specific subpopulations of tabular data, known as error slices. Learning robust representation in presence o…

DecoderLanguage ModelingLanguage ModellingMasked Language Modeling+2

Progressive Feature Upgrade in Semi-supervised Learning on Tabular Domain

2022-12-01 · Morteza Mohammady Gharasuie, Fenjiao Wang

Recent semi-supervised and self-supervised methods have shown great success in the image and text domain by utilizing augmentation techniques. Despite such success, it is not easy to transfer this success to tabular doma…

Understanding the limitations of self-supervised learning for tabular anomaly detection

2023-09-15 · Kimberly T. Mai, Toby Davies, Lewis D. Griffin

While self-supervised learning has improved anomaly detection in computer vision and natural language processing, it is unclear whether tabular data can benefit from it. This paper explores the limitations of self-superv…

Anomaly DetectionSelf-Supervised Learning

SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning

2021-10-08 · NeurIPS 2021 12 · Talip Ucar, Ehsan Hajiramezanali, Lindsay Edwards

Self-supervised learning has been shown to be very effective in learning useful representations, and yet much of the success is achieved in data types such as images, audio, and text. The success is mainly enabled by tak…

Collaborative InferenceContrastive LearningRepresentation LearningSelf-Supervised Learning

VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain

2020-12-01 · NeurIPS 2020 12 · Jinsung Yoon, Yao Zhang, James Jordon, Mihaela van der Schaar

Self- and semi-supervised learning frameworks have made significant progress in training machine learning models with limited labeled data in image and language domains. These methods heavily rely on the unique structure…

Data AugmentationImputationSelf-Supervised Learning